Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2328 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.6602. Min Act: -0.0001

Data Index: 115117 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.5353. Min Act: -0.0001

Data Index: 232527 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2214. Min Act: -0.0001

Data Index: 77863 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.1729. Min Act: -0.0001

Data Index: 1050499 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.0689. Min Act: -0.0001

Data Index: 438881 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.0202. Min Act: -0.0001

Data Index: 304520 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.0334. Min Act: -0.0001

Data Index: 99052 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.0139. Min Act: -0.0001

Data Index: 569968 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.9183. Min Act: -0.0001

Data Index: 35328 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.9363. Min Act: -0.0001

Data Index: 40728 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.9079. Min Act: -0.0001

Data Index: 1277138 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.8264. Min Act: -0.0001

Data Index: 7291 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.8863. Min Act: -0.0001

Data Index: 584276 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.8814. Min Act: -0.0001

Data Index: 718425 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.9042. Min Act: -0.0001

Data Index: 767999 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.8612. Min Act: -0.0001

Data Index: 336506 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.8585. Min Act: -0.0001

Data Index: 379298 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.8270. Min Act: -0.0001

Data Index: 1272256 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.8183. Min Act: -0.0001

Data Index: 1086893 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 1.6602. Min Range: -1.6602

Max Act: 0.8140. Min Act: -0.0001

Data Index: 553721 (C4 (Web Text))

Max Activating Token Index: 725